Skip to main content
Technology in Cancer Research & Treatment logoLink to Technology in Cancer Research & Treatment
. 2025 Dec 26;24:15330338251410073. doi: 10.1177/15330338251410073

Molecular Imaging in Early Skin Cancer Detection: Advances, Limitations, and Future Directions

Elizabeth Berry 1, Reid F Thompson 2, Catherine Shachaf 3,, Sancy Leachman 4
PMCID: PMC12745521  PMID: 41451881

Abstract

Early detection of skin cancer is crucial for effective treatment and improved patient outcomes. Recent advancements in oncologic imaging, particularly molecular imaging techniques, have revolutionized cancer diagnostics and treatment by enabling the visualization of tumors and cellular activities at the molecular level. These techniques facilitate the identification of early-stage cancers that might remain undetectable through traditional imaging methods. Innovative technologies such as reflectance confocal microscopy (RCM) and optical coherence tomography (OCT) which visualize skin at near-histologic detail and skin fluorescent imaging (SFI), which targets αvβ3 integrin expression, are promising for non-invasive early detection of melanoma. By integrating in vivo molecular imaging with tumor biomarkers, clinicians can gain more precise insights into processes integral to cancer biology, leading to improved diagnosis, prognosis and the development of personalized treatment strategies. This review explores imaging modalities used in skin cancer diagnosis, highlighting their advantages and limitations, with an emphasis on molecular imaging, stressing its potential to improve early detection, personalize treatment and monitor therapeutic responses.

Keywords: Review, stroma, tumor microenvironment, biomarker, melanoma, nevus, tissue remodeling, in vivo imaging, αvβ3 integrin, SFI

Introduction

Early cancer detection is crucial. It enables less aggressive treatment, preserves healthy tissue, improves quality of life, lowers costs and reduces mortality through timely intervention. 1 Compared with standard biopsy and histology, imaging is less invasive and more effective for tumor analysis, offering a comprehensive, dynamic view of the tumor and its microenvironment rather than a static snapshot.

Over the past century, medical imaging has evolved dramatically; from the early use of x-rays for basic structural visualization, to the development of computed tomography (CT), magnetic resonance imaging (MRI) and positron emission tomography (PET), which have allowed increasingly detailed insights into both anatomy and function. Today, the field is entering a new era of precision, where imaging is no longer limited to structure or metabolism and can extend into molecular characterization of disease. Emerging modalities and hybrid platforms now offer the ability to visualize specific molecular targets, cellular processes and dynamic interactions within the stromal tumor microenvironment (STE). This convergence of imaging and biomarker science holds transformative potential for early diagnosis, therapeutic monitoring and personalized treatment strategies, underscoring the need for an up-to-date, integrative review of recent advances and future directions.

Cancer diagnostics and treatment are moving toward personalized medicine, with a focus on precise radiotracer targeting and theranostics – the integration of diagnostic testing with targeted therapy – to enhance imaging sensitivity and specificity and drug delivery/treatment. 2 Advancements in resolution and novel imaging probes hold considerable promise for the future.

Molecular imaging offers focused, in vivo visualization of tumor heterogeneity, angiogenesis and treatment monitoring by focusing on proteins, receptors and metabolic processes.3,4 By targeting molecular rather than structural changes, this form of imaging offers the ability to non-invasively identify molecular changes and provides a deeper understanding of disease mechanisms, particularly important during early disease stages.57

Molecular imaging technologies in oncology face significant challenges, including spatial limitations, interpretative variability and concerns over cost and accessibility. 7 In terms of the latter, expensive and complex imaging modalities like PET/MRI are in stark contrast to more affordable and widely available options like ultrasound, optical imaging and SFI.

Tumor heterogeneity can significantly impact the accuracy of molecular imaging since it relies on specific biomarkers, which are often differentially expressed throughout a tumor. 8 This can lead to discrepancies in assessments of tumor size and extent, potentially causing false negatives or underestimating spread. Consequently, this can affect treatment as imaging may only show the destruction of cells with the target biomarker, while resistant, non-targeted cell populations continue to thrive and grow.

This review summarizes key imaging modalities currently used in skin cancers in its various stages, highlighting their clinical applications and comparative advantages. For more detailed technical discussions, readers are referred to comprehensive texts and specialized reviews.

Imaging modalities (Tables 1 and 2)

Table 1.

Representative Images from various Imaging Modalities.

graphic file with name 10.1177_15330338251410073-table1.jpg

Table 2.

In Vivo Imaging Techniques.

Technique Depth; Resolution/Scope Key Applications Targeted Features Advantages Limitations Examples
MRI1824 High-resolution anatomical imaging; whole body, 1–2 mm3 resolution. Tumor size, location, perfusion Vascular permeability, tissue invasion Noninvasive, detailed insights Expensive, limited molecular specificity, certain patients eg with ICD/pacemaker and other implantables) DCE-MRI, DW-MRI, BOLD MRI, TOLD MRI, CEST MRI
PET2527 Functional imaging with tracers; whole body, 4–5 mm resolution Metabolic activity, hypoxia Glucose metabolism, marker visualization High sensitivity, metabolic insights Low spatial resolution, radioactive tracers FMISO for tumor hypoxia, 89Zr-nanoreporters for nanotherapy, tracking glycolysis
Optical Imaging 28 Real-time, sensitive imaging; High-resolution optical imaging penetrates ≤1 mm, while deeper techniques (OCT, DOT, photoacoustics) reach mm–cm with lower resolution. Immune cell tracking, gene expression Molecular events, immune activity Noninvasive, live process visualization Limited tissue penetration PAI, Intravital Microscopy, Bioluminescence Imaging, Fluorescence Imaging, FMT, OCT
Multiphoton Microscopy 29 High-resolution in live tissue; 1–4 mm depth, ECM remodeling, cellular interactions Immune cell behavior, ECM architecture Subcellular resolution, live insights Limited depth, specialized equipment 2PFM (up to 1 mm), 3PFM (3-4 mm), SHG, THG
Ultrasound Imaging30,31 Real-time, noninvasive imaging; ∼2–15 cm; 0.3–0.5 µm lateral, ∼1 µm axial Tumor size, vascularity, blood flow Tumor angiogenesis, vessel architecture Cost-effective, portable Limited molecular information UTMD, CEUS, AI-integrated ultrasound
Molecular Imaging3,4 Targeted molecular visualization; broad range as it includes multiple modalities. Tumor heterogeneity, treatment monitoring Proteins, receptors, metabolic processes Early detection, personalized therapy Expensive, specialized probes 18F-FDG PET/CT, Fluorescence imaging, Combination molecular probes, Emerging tracers

Whole Body/Deep-Tissue Imaging

Magnetic Resonance Imaging (MRI) provides high-resolution in vivo anatomical imaging, making it a valuable tool for assessing tumor size, location, tissue cellularity and perfusion.1824 It is particularly valuable in assessing the extent of skin tumor invasion in the head and neck regions, where accurate delineation of tumor boundaries is crucial for surgical planning. 32

MRI uses strong magnetic fields and radiofrequency pulses to detect signals from hydrogen nuclei in water molecules, generating detailed images of soft tissues. It is particularly effective in evaluating vascular permeability and surrounding tissue invasion. Its noninvasive nature allows for detailed structural and functional insights, though it is expensive and has limited molecular specificity. Specialized techniques such as Dynamic Contrast-Enhanced MRI (DCE-MRI), Diffusion-Weighted MRI (DW-MRI), Blood Oxygen Level-Dependent (BOLD) MRI, Tissue Oxygen Level-Dependent (TOLD) MRI and Chemical Exchange Saturation Transfer (CEST) MRI enhance its application in tumor characterization. Typical resolution is approximately 1–2 mm3. MRI can detect tumors as small as 6.9 mm (mean size for ductal carcinoma in situ) and 9.3 mm (mean size for invasive cancers). 33 MRI has limitations, including safety concerns for patients with metallic implants like pacemakers and reduced effectiveness in imaging tumors with low water content or calcified structures, such as certain bone or mucinous tumors. 34 It provides structural and anatomical information, not metabolic or other cellular activity.

Positron Emission Tomography (PET) provides functional in vivo imaging using radiolabeled tracers to assess metabolic activity, hypoxia and receptor expression.2527 PET imaging is utilized to detect and monitor metastatic melanoma, particularly in stages III and IV, where it helps identify metastases and assess treatment response. 35

PET detects gamma rays emitted indirectly by a radioactive tracer that accumulates in metabolically active tissues, producing functional images of biological processes. By enabling visualization of radiolabeled tracers that target specific markers such as glucose metabolism, receptor expression, proliferation, hypoxia, or immune activity. PET offers high sensitivity for metabolic and molecular insights, though it requires radioactivity and has low spatial resolution, making it potentially harmful to health and less precise in pinpointing the exact location of abnormalities.

PET is useful for tracking nanotherapy biodistribution, predicting nanotherapy response using zirconium-89 nanoreporters, imaging tumor hypoxia with FMISO, measuring tumor vasculature and permeability and visualizing metabolic processes like glycolysis and choline-phospholipid metabolism. Typical spatial resolution is approximately 4–5 mm and PET can detect tumors as small as 7 mm, corresponding to the detection of tumors with a volume of 0.2 ml in a 5:1 tumor-to-background ratio. 36 The most widely used molecular imaging modality overall, 18F-fluorodeoxyglucose (FDG) PET/CT assesses cancer metabolism by tracking uptake of the 18F-FDG radiotracer. Other notable advances in molecular imaging include fluorescence imaging with targeted fluorescent probes for tissue visualization; dual-modality probes that combine radioisotopes and fluorescence for enhanced imaging; and emerging radiotracers beyond 18F-FDG, such as 68Ga-DOTATATE for neuroendocrine tumors, 89Zr-huJ591 and 18F-DCFPyL for prostate-specific membrane antigen (PSMA), and 18F-alfatide for assessing angiogenesis. Finally, there are new PET scans using radiolabeled tags identifying CD8 cells to differentiate tumor progression from pseudoprogression in the context of immunotherapy. 37

Intermediate to Deep Tissue Imaging (∼2-15 cm)

Ultrasound imaging is an in vivo, noninvasive method for assessing tumor size, vascularity and blood flow, particularly useful in evaluating tumor angiogenesis and vessel architecture.30,31 It is used in skin cancer to non-invasively assess tumor thickness, delineate margins, evaluate regional lymph nodes and monitor for recurrence, providing structural and procedural guidance complementary to molecular or histologic imaging modalities. 38

The ultrasound probe sends high-frequency sound waves into the body and detects echoes reflected from tissue interfaces to create real-time images of internal structures. As a cost-effective and portable technique, ultrasound enables dynamic imaging, though it provides limited molecular information, limited visualization in certain tissues (bone, air-filled areas), lower sensitivity for small or early-stage cancers and low specificity for malignant tissue. Advancements such as ultrasound-targeted microbubble destruction enhance drug delivery and contrast-enhanced ultrasound improves visualization of blood flow and tissue perfusion. Typical resolution for conventional ultrasound is approximately 1–2 mm; High-frequency ultrasound approximately 30–100 µm. Super-resolution ultrasound imaging (SRI) has demonstrated the capability to visualize microvasculature, aiding in the differential diagnosis of breast masses. 39

Shallow to Intermediate Depth Imaging (∼1-2 cm)

Optical imaging enables in vivo, highly sensitive imaging of immune cell tracking, gene expression and target distribution, providing crucial insights into cellular and molecular events as well as immune activity. 28 Optical imaging modalities provide non-invasive, high-resolution visualization of skin architecture, enabling early detection, margin assessment and monitoring of malignant lesions while reducing unnecessary biopsies.

This technology uses visible or near-infrared light to visualize tissues labeled with fluorescent or bioluminescent markers, enabling high-sensitivity imaging of surface or shallow structures. Its noninvasive nature allows for real-time visualization of live processes, yet its limitation lies in restricted tissue penetration. Optical imaging comprises multiple different modalities including photoacoustic imaging (research; clinical trials ongoing), intravital microscopy (research; preclinical trials ongoing), bioluminescence imaging (research; preclinical, genetically modified cells required), fluorescence imaging (used in clinical setting, specifically intraoperatively), fluorescence molecular tomography (research; preclinical) and optical coherence tomography (widely used in ophthalmology clinics). Photoacoustic imaging visualizes tumor vasculature and measures tissue oxygenation. Intravital microscopy provides subcellular-resolution imaging of STE in living organisms. Bioluminescence imaging is used to track cancer cell movement and monitor tumor-stroma interactions. Fluorescence imaging can detect single cells and visualize dynamic interactions between cancer cells. Fluorescence molecular tomography enables 3D imaging of molecular targets, such as matrix metalloproteinases (MMPs) and tumor vasculature. Lastly, optical coherence tomography (OCT) offers label-free imaging of tissue structures and vascular networks with micrometer-scale resolution. Typical resolution is approximately 10 µm. Optical imaging can detect tumors with an average imaging depth of 0.65 mm and a resolution of 10 µm. 7

Superficial Imaging (≤1 mm Depth)

Reflectance confocal microscopy (RCM) is a non-invasive imaging technique which provides high-resolution, in vivo visualization of the skin at a cellular level. Utilizing a low-power laser (usually with a wavelength of 830 nm) to provide high-resolution, label-free imaging by detecting variations in tissue refractive indices and the principle of light reflectance, RCM captures detailed images of the epidermis and superficial dermis without the need for a biopsy. It offers lateral resolution of approximately 0.5–1.0 micrometers and axial resolution around 3–5 micrometers. RCM aids in diagnosing skin cancers, evaluating various inflammatory skin conditions, and monitoring treatment response, offering a rapid and accurate alternative to more invasive methods. 40

Multiphoton microscopy enables high-resolution imaging in live tissues, facilitating the study of cellular interactions and extracellular matrix (ECM) remodeling. 29 It can be used in vivo (especially in intravital microscopy with implanted imaging windows), though usually limited to superficial tissues (so far available in research and preclinical trials in humans) or small animal models due to shallow imaging depth. Multiphoton microscopy employs near-infrared lasers to excite fluorescent molecules via simultaneous absorption of two or more photons, allowing deep, high-resolution imaging of living tissues. Two-photon fluorescence microscopy allows imaging up to 1 mm deep in mouse brains for detailed cellular structure studies, three-photon fluorescence microscopy extends imaging depth to 3–4 mm with enhanced contrast and reduced background, second harmonic generation microscopy provides label-free detection of non-centrosymmetric structures such as collagen and myosin, while third harmonic generation microscopy contrasts optical inhomogeneities within tissues. Typical resolution is approximately 0.3–0.5 µm lateral, ∼1 µm axial). Multiphoton microscopy enables high-resolution imaging of tumor and normal tissue characteristics, allowing for the visualization of cellular morphology and microstructures. 41

Molecular Imaging of the Stromal Tumor Environment (STE) – Focus on Fluorescence

Molecular imaging techniques use probes that target specific markers within the STE to visualize proteins, receptors and metabolic processes. These methods provide valuable insights into tumor heterogeneity and help identify potential therapeutic targets. They deepen our understanding of tumor biology, angiogenesis and treatment response, thereby enhancing early detection, enabling personalized treatment and allowing real-time monitoring of therapeutic outcomes.4244 Advances in molecular imaging and a deeper understanding of the STE hold great promise for transforming cancer diagnosis and treatment, particularly for melanoma, one of the most aggressive forms of skin cancer.45,46 Melanoma's accessibility and visible traits make it an ideal model for studying the STE's role in cancer development. 47

Molecular imaging allows for visualizing stromal remodeling, providing a powerful tool for early cancer detection (Table 3). Methodologies include MRI (visualizing tumor vasculature, stromal cells and ECM), PET (targeting CAFs, immune cells, tumor vasculature and angiogenesis), fluorescence imaging (including Intravital Microscopy, Fluorescence Lifetime Imaging Microscopy (FLIM) and probes targeting stromal elements), photoacoustic imaging (PAI; imaging tumor vasculature and angiogenesis, melanin content), Mass Spectrometry Imaging (MSI), Ultrasound and Optical Coherence Tomography (OCT).

Table 3.

Molecular Imaging Modalities and Biomarkers/Targets for Melanoma Stroma.

Modality Stromal Applications in Melanoma Biomarkers/Targets
Positron Emission Tomography (PET) 48 Imaging and quantification of CAFs and their distribution. Fibroblast Activation Protein (FAP) using FAPI tracers; potentially other targets on stromal cells or matrix components. Can be used in vivo.
Magnetic Resonance Imaging (MRI)49,50 Assessing ECM composition, cellularity and vascular permeability. Water diffusion (DWI) reflects cellular density; T1ρ relaxation can indicate collagen content; Ktrans (Blood Transfer Rate Constant), contrast agents for vascularity. Can be used in vivo.
Fluorescence Imaging 51 Visualizing immune cell infiltration and interactions, ECM structure and metabolic state in vivo. Fluorescent proteins or dyes for cell labeling; autofluorescence of collagen/elastin; metabolic cofactors (NADH, FAD) for FLIM; targeted fluorescent probes such as ORL1 for αvβ3 integrin expression (SFI). Can be used in vivo.
Photoacoustic Imaging (PAI) 12 Imaging tumor vasculature, blood oxygenation and melanin distribution within the stroma. Leverages endogenous signals (melanin, hemoglobin, collagen) and exogenous agents (gold nanoparticles, ICG) to target markers like α-MSH receptors and melanoma antigens for enhanced tumor detection. Can be used in vivo (still in research).
Mass Spectrometry Imaging (MSI) 52 Analyzing the molecular composition and heterogeneity of the STE. Reveals overexpression of vimentin and actin (linked to metastasis and invasion), elevated histones H2B/H4 (epigenetic dysregulation), reduced collagen (structural changes) and decreased DNA-3-methyladenine glycosylase (impaired DNA repair). Cannot be used in vivo.
Ultrasound 53 Assessing stromal architecture, vascularity (with contrast agents) and tissue stiffness. Tissue density and elasticity; microbubbles (exogenous contrast agents) for vascular imaging. Can be used in vivo.
Optical Coherence Tomography (OCT) 54 Providing high-resolution structural imaging of the skin and superficial stroma. Targets include lesion architecture (0.5-1.5 mm depth), irregular dermo-epidermal junctions, atypical melanocytes, pagetoid spread, distorted rete ridges, neovascular patterns (via SV-OCT), vertical “icicle” structures, and collagen loss. Can be used in vivo.

Our understanding of the STE, also known as the tumor microenvironment (TME), in cancer initiation and progression has evolved significantly. 55 Despite its critical role in cancer development, the STE is often overlooked. The STE is a complex ecosystem comprising the extracellular matrix (ECM), cancer-associated fibroblasts (CAFs), the tumor vasculature and a variety of immune cells. These shape melanoma progression, drive therapy resistance and promote the spread of cancer to distant sites.5658 Rather than viewing cancer solely as uncontrolled cell growth, research now highlights the complex interactions between various cell types and the physicochemical components of the STE, particularly the ECM and neoangiogenesis. 55

Stromal cells, through integrin signaling and microenvironment interactions, drive key processes such as migration, survival, angiogenesis and proliferation.58,59 By fostering tumor growth, immune evasion and heterogeneity, the STE contributes to therapy resistance, making it a crucial focus in cancer research. Investigating this intricate network could enable earlier cancer detection, potentially before angiogenesis even begins.

Fluorescence imaging is a versatile technique which offers high molecular specificity when combined with targeted fluorescent probes. It also allows for real-time visualization of biological processes, making it valuable for surgical guidance. However, a key limitation of fluorescence imaging in vivo is its limited penetration depth in tissues due to light scattering and absorption (making it ideal for skin), as well as the potential for interference from autofluorescence, which is the natural fluorescence emitted by biological tissues.

A new molecular fluorescence technology for examining the STE is Skin Fluorescent Imaging (SFI), which leverages molecular imaging techniques to assess alterations in integrin expression within the STE. 17 The SFI system represents an advancement in melanoma detection, offering a noninvasive, accurate and cost-effective alternative to traditional diagnostic methods. SFI uses an amino acid target tagged with a fluorescent molecular dye – arginine-glycine-aspartic acid (RGD) – to non-invasively detect tissue remodeling in melanoma, a tumor biomarker targeting αvβ3 integrin receptor expressed on blood vessels yet absent in normal tissues. 60 Its fluorescent tag is topically applied, providing a safer and more convenient option than PET imaging, which requires injected radiotracers. One of SFI's most compelling features is its ability to deliver immediate results, reducing patient anxiety and eliminating unnecessary follow-up appointments. With 100% sensitivity and 95.7% specificity for melanoma, 17 it significantly minimizes false negatives and unnecessary biopsies, improving diagnostic accuracy. Unnecessary biopsies introduce risks, including infection, pain and scarring. Early detection capability enhances treatment outcomes and increases quality-adjusted life years (QALYs) for patients, while also lowering healthcare costs by reducing histopathological examinations and associated complications.61,62 Radiolabeled integrin-binding RGD peptides have been used for imaging solid cancers via i.v. administration 63 in melanoma, 64 breast cancer 65 and other advanced solid tumors. 66 In melanoma, αvβ3 integrin receptor expression has been associated with aggressive disease. 67

Targeted Cancer Imaging – Future Directions and Limitations

Appropriate selection of imaging modality is dependent on tumor type, patient demographics and underlying cancer biology. The most effective imaging tool is often specific to the cancer's location and characteristics; for instance, CT scans are frequently used for lung cancer, while MRI is the preferred modality for breast cancer due to its superior soft tissue contrast. 68 Beyond tumor type, patient demographics can influence modality choice and patient satisfaction. Studies have shown that satisfaction with imaging varies by age, with the highest satisfaction rates among patients aged 70–79 and the lowest among those aged 20–29. Choices can also be influenced by factors like patient age, sex, overall health and personal preference. 69

Morphology-based tools such as RCM, multiphoton microscopy and OCT achieve high sensitivity for detecting histopathological abnormalities in tissue architecture yet show low specificity, leading to false positives and unnecessary biopsies. Deeper imaging methods such as MRI, PET and ultrasound are valuable for staging or assessing lesion depth, yet they are costly and lack specificity at the level of the lesion itself (in contrast to metastases). By contrast, the SFI System leverages αvβ3 integrin as a biomarker of angiogenesis to increase specificity for biologically aggressive lesions while maintaining sensitivity for early melanoma detection. While SFI promises a superior balance of accuracy and cost-effectiveness, multi-site validation will be essential to confirm its performance across clinical contexts.

Autofluorescence, motion artifacts and probe variability impact the performance of various imaging modalities. Autofluorescence affects optical imaging techniques like RCM and OCT, where the natural fluorescence of tissue can be used as a diagnostic signal for changes in tissue composition indicative of cancer, though it can also be a source of background noise that interferes with molecular probes. 70 In deep-tissue imaging such as PET, CT and MRI, motion artifacts are a significant challenge, as involuntary movements from breathing or a heartbeat can cause image blurring, and inaccurate tumor quantification. 71 To address this, these modalities often employ motion correction techniques like respiratory and cardiac gating. Finally, probe variability is a key consideration for molecular imaging modalities like PET, which rely on injected agents to create an image. Inconsistencies in a probe's binding affinity, specificity, and clearance from non-target tissues can lead to false-positive results and limit the reliability and clinical application of the technology.

SFI offers exceptional cost-effectiveness by providing accurate, point-of-care melanoma risk assessment, potentially reducing unnecessary procedures among the >5 million skin biopsies performed annually in the U.S., most of which prove benign. Unlike high-cost modalities such as MRI and PET, or advanced optical tools like multiphoton microscopy, RCM and OCT, which require expensive equipment and specialist interpretation yet cannot significantly cut biopsy rates, SFI is low-cost and easy to use. Even ultrasound, though inexpensive, lacks the molecular specificity to meaningfully reduce unnecessary procedures.

Artificial intelligence (AI) is transforming biomedical imaging across a wide range of modalities by enhancing diagnostic accuracy, speeding up workflows and making advanced analysis more accessible. 72 From high-resolution techniques like OCT, 73 multiphoton microscopy 74 and mass spectrometry imaging 75 to widely used platforms like MRI, 76 PET, 77 ultrasound 78 and optical imaging, 79 AI enables faster reconstruction, automated lesion detection and nuanced tissue characterization. These advances not only improve clinical outcomes, such as non-invasive melanoma screening with RCM 80 or early tumor detection with PET and OCT, 73 they also expand imaging access to underserved settings through real-time guidance and mobile diagnostics. Collectively, AI accelerates the shift toward more precise, scalable and patient-centered care.

Notably, among the imaging modalities surveyed, PET 81 and MRI 82 are the most effective and widely used for detecting metastases, offering whole-body metabolic insights and high-resolution soft tissue imaging, respectively. Ultrasound, 83 PAI 84 and MSI85,86 serve more limited or emerging roles, while modalities like RCM, OCT and SFI are not suitable for metastasis detection due to their localized or surface-level focus.

Sensitivity and specificity across different imaging modalities also depend on whether cancers are in early or late stages. For whole body and deep-tissue imaging, modalities like PET and MRI can detect small, early-stage tumors and are also highly effective for late-stage cancers and metastasis detection.87,88 CT scans have low sensitivity for diagnosing early-stage colon cancer. 89 For intermediate depth imaging, ultrasound is cost-effective and portable for breast cancer detection. 90 In shallow and superficial imaging, RCM and OCT have high sensitivity for early-stage histopathological abnormalities yet are not suitable for late-stage cancers because they cannot penetrate deep into the body.91,92 Molecular imaging such as SFI, shows exceptional sensitivity and high specificity for early melanoma detection. 17

Imaging methodologies raise important ethical considerations, including informed consent, radiation exposure and incidental findings. Patients undergoing procedures such as CT and PET face a small risk of developing cancer later in life due to ionizing radiation, 93 while modalities using injected agents, like MRI and PET, carry potential side effects such as allergic reactions or toxicity in sensitive individuals. Advanced imaging also increases the likelihood of incidental findings – unexpected discoveries unrelated to the original reason for the scan – which can create ethical dilemmas about patient communication and follow-up. These issues may lead to patient anxiety, financial strain and overdiagnosis of slow-growing tumors. Ensuring patients are fully informed of the risks and benefits before procedures is therefore critical.

Conclusion

The integration of molecular imaging represents a significant advancement in the early detection and personalized treatment of cancer. These technologies provide detailed insights into tumor biology, enabling clinicians to identify early-stage cancers which might be missed by traditional methods. Various imaging modalities, including MRI, PET, optical imaging, multiphoton microscopy and ultrasound, each offer unique advantages in visualizing tumors and cellular activities. Molecular imaging, particularly techniques like SFI, offers non-invasive, accurate and real-time visualization of cancer-associated molecular changes, enhancing diagnostic precision and treatment monitoring. By focusing on the STE and leveraging specific biomarkers, these approaches improve early detection and allow for personalization of therapeutic strategies and monitoring of treatment efficacy. The continued development and clinical validation of these innovative technologies hold great promise for transforming cancer care, with the potential to improve patient outcomes and reduce healthcare costs.

Acknowledgements

Dr Yoav Litvin and Anne Callahan assisted in preparing and reviewing the manuscript.

Footnotes

Ethics Statement: N/A

Funding: Orlucent, Inc.

The authors declared no potential conflicts of interest with respect to the research, authorship, and/or publication of this article.

References

  • 1.Crosby D, Bhatia S, Brindle KM, et al. Early detection of cancer. Science. 2022;375(6586):eaay9040. doi: 10.1126/science.aay9040 [DOI] [PubMed] [Google Scholar]
  • 2.Solnes LB, Werner RA, Jones KM, et al. Theranostics: Leveraging molecular imaging and therapy to impact patient management and secure the future of nuclear medicine. J Nucl Med. 2020;61(3):311–318. doi: 10.2967/jnumed.118.220665 [DOI] [PubMed] [Google Scholar]
  • 3.Chen K, Chen X. Design and development of molecular imaging probes. Curr Top Med Chem. 2010;10(12):1227–1236. doi: 10.2174/156802610791384225 [DOI] [PMC free article] [PubMed] [Google Scholar]
  • 4.Solomon SB, Cornelis F. Interventional molecular imaging. J Nucl Med. 2016;57(4):493–496. doi: 10.2967/jnumed.115.161190 [DOI] [PMC free article] [PubMed] [Google Scholar]
  • 5.Florea A, Mottaghy FM, Bauwens M. Molecular imaging of angiogenesis in oncology: Current preclinical and clinical status. Int J Mol Sci. 2021;22(11):5544. [DOI] [PMC free article] [PubMed] [Google Scholar]
  • 6.James ML, Gambhir SS. A molecular imaging primer: Modalities, imaging agents, and applications. Physiol Rev. 2012;92(2):897–965. doi: 10.1152/physrev.00049.2010 [DOI] [PubMed] [Google Scholar]
  • 7.Rowe SP, Pomper MG. Molecular imaging in oncology: Current impact and future directions. CA Cancer J Clin. 2022;72(4):333–352. [DOI] [PMC free article] [PubMed] [Google Scholar]
  • 8.Fisher R, Pusztai L, Swanton C. Cancer heterogeneity: Implications for targeted therapeutics. Br J Cancer. 2013;108(3):479–485. doi: 10.1038/bjc.2012.581 [DOI] [PMC free article] [PubMed] [Google Scholar]
  • 9.Furdová A, Sramka M, Thurzo A, et al. Early experiences of planning stereotactic radiosurgery using 3D printed models of eyes with uveal melanomas. Clin Ophthalmol. 2017;11:267–271. doi: 10.2147/OPTH.S123640 [DOI] [PMC free article] [PubMed] [Google Scholar]
  • 10.Hirota K, Yoshimura C, Kubo O, et al. Primary intracranial malignant melanoma with extracranial metastasis. J Korean Neurosurg Soc. 2017;60(1):98–101. doi: 10.3340/jkns.2015.0506.007 [DOI] [PMC free article] [PubMed] [Google Scholar]
  • 11.Wortsman X. Sonography of the primary cutaneous melanoma: A review. Radiol Res Pract. 2012;2012:814396. [DOI] [PMC free article] [PubMed] [Google Scholar]
  • 12.Fakhoury JW, Lara JB, Manwar R, et al. Photoacoustic imaging for cutaneous melanoma assessment: A comprehensive review. J Biomed Opt. 2024;29(Suppl 1):S11518. [DOI] [PMC free article] [PubMed] [Google Scholar]
  • 13.Materin MA, Raducu R, Bianciotto C, et al. Fundus autofluorescence and optical coherence tomography findings in choroidal melanocytic lesions. Middle East Afr J Ophthalmol. 2010;17(3):201–206. doi: 10.4103/0974-9233.65489 [DOI] [PMC free article] [PubMed] [Google Scholar]
  • 14.Scope A, Longo C. Recognizing the benefits and pitfalls of reflectance confocal microscopy in melanoma diagnosis. Dermatol Pract Concept. 2014;4(3):67–71. doi: 10.5826/dpc.0403013 [DOI] [PMC free article] [PubMed] [Google Scholar]
  • 15.Morosi L, Spinelli P, Zucchetti M, et al. Determination of paclitaxel distribution in solid tumors by nano-particle assisted laser desorption ionization mass spectrometry imaging. PLoS One. 2013;8(8):e72532. doi: 10.1371/journal.pone.0072532 [DOI] [PMC free article] [PubMed] [Google Scholar]
  • 16.Das A, Monteiro M, Barai A, et al. MMP Proteolytic activity regulates cancer invasiveness by modulating integrins. Sci Rep. 2017;7(1):14219. doi: 10.1038/s41598-017-14340-w [DOI] [PMC free article] [PubMed] [Google Scholar]
  • 17.Shachaf A, Manbeck K, Yang G, et al. Molecular skin fluorescence imaging: A tool for evaluating early melanoma development. Pigment Cell Melanoma Res. 2024;37(1):372–377. doi: 10.1111/pcmr.13159 [DOI] [PubMed] [Google Scholar]
  • 18.Karageorgis A, Dufort S, Sancey L, et al. An MRI-based classification scheme to predict passive access of 5 to 50-nm large nanoparticles to tumors. Sci Rep. 2016;6:21417. doi: 10.1038/srep21417 [DOI] [PMC free article] [PubMed] [Google Scholar]
  • 19.Matsuo K, Kamada R, Mizusawa K, et al. Specific detection and imaging of enzyme activity by signal-amplifiable self-assembling (19)F MRI probes. Chemistry. 2013;19(38):12875–12883. doi: 10.1002/chem.201300817 [DOI] [PubMed] [Google Scholar]
  • 20.Turnbull LW. Dynamic contrast-enhanced MRI in the diagnosis and management of breast cancer. NMR Biomed. 2009;22(1):28–39. doi: 10.1002/nbm.1273 [DOI] [PubMed] [Google Scholar]
  • 21.Amornsiripanitch N, Bickelhaupt S, Shin HJ, et al. Diffusion-weighted MRI for unenhanced breast cancer screening. Radiology. 2019;293(3):504–520. doi: 10.1148/radiol.2019182789 [DOI] [PMC free article] [PubMed] [Google Scholar]
  • 22.O’Connor JPB, Robinson SP, Waterton JC. Imaging tumour hypoxia with oxygen-enhanced MRI and BOLD MRI. Br J Radiol. 2019;92(1095):20180642. doi: 10.1259/bjr.20180642 [DOI] [PMC free article] [PubMed] [Google Scholar]
  • 23.McCabe A, Martin S, Shah J, et al. T(1) based oxygen-enhanced MRI in tumours; a scoping review of current research. Br J Radiol. 2023;96(1146):20220624. doi: 10.1259/bjr.20220624 [DOI] [PMC free article] [PubMed] [Google Scholar]
  • 24.Cai K, Xu HN, Singh A, et al. Breast cancer redox heterogeneity detectable with chemical exchange saturation transfer (CEST) MRI. Mol Imaging Biol. 2014;16(5):670–679. doi: 10.1007/s11307-014-0739-y [DOI] [PMC free article] [PubMed] [Google Scholar]
  • 25.Lee H, Shields AF, Siegel BA, et al. (64)Cu-MM-302 positron emission tomography quantifies variability of enhanced permeability and retention of nanoparticles in relation to treatment response in patients with metastatic breast cancer. Clin Cancer Res. 2017;23(15):4190–4202. doi: 10.1158/1078-0432.CCR-16-3193 [DOI] [PMC free article] [PubMed] [Google Scholar]
  • 26.Huang R, Wang M, Zhu Y, et al. Development of PET probes for cancer imaging. Curr Top Med Chem. 2015;15(8):795–819. doi: 10.2174/1568026615666150302110325 [DOI] [PubMed] [Google Scholar]
  • 27.Moody AS, Dayton PA, Zamboni WC. Imaging methods to evaluate tumor microenvironment factors affecting nanoparticle drug delivery and antitumor response. Cancer Drug Resist. 2021;4(2):382–413. [DOI] [PMC free article] [PubMed] [Google Scholar]
  • 28.Crisp JL, Savariar EN, Glasgow HL, et al. Dual targeting of integrin αvβ3 and matrix metalloproteinase-2 for optical imaging of tumors and chemotherapeutic delivery. Mol Cancer Ther. 2014;13(6):1514–1525. doi: 10.1158/1535-7163.MCT-13-1067 [DOI] [PMC free article] [PubMed] [Google Scholar]
  • 29.Xu C, Nedergaard M, Fowell DJ, et al. Multiphoton fluorescence microscopy for in vivo imaging. Cell. 2024;187(17):4458–4487. doi: 10.1016/j.cell.2024.07.036 [DOI] [PMC free article] [PubMed] [Google Scholar]
  • 30.Zhang G, Ye H, Sun,Y, Guo, Z. Ultrasound molecular imaging and its applications in cancer diagnosis and therapy. ACS Sens. 2022;7(10):2857–2864. [DOI] [PubMed] [Google Scholar]
  • 31.Abou-Elkacem L, Bachawal SV, Willmann JK. Ultrasound molecular imaging: Moving toward clinical translation. Eur J Radiol. 2015;84(9):1685–1693. doi: 10.1016/j.ejrad.2015.03.016 [DOI] [PMC free article] [PubMed] [Google Scholar]
  • 32.Chang PC, Fischbein NJ, McCalmont TH, et al. Perineural spread of malignant melanoma of the head and neck: Clinical and imaging features. AJNR Am J Neuroradiol. 2004;25(1):5–11. [PMC free article] [PubMed] [Google Scholar]
  • 33.Sanderink WBG, Caballo M, Strobbe LJA, et al. Reliability of MRI tumor size measurements for minimal invasive treatment selection in small breast cancers. Eur J Surg Oncol. 2020;46(8):1463–1470. doi: 10.1016/j.ejso.2020.04.038 [DOI] [PubMed] [Google Scholar]
  • 34.Elbanna KY, Kielar AZ. Computed tomography versus magnetic resonance imaging for hepatic lesion characterization/diagnosis. Clin Liver Dis (Hoboken). 2021;17(3):159–164. doi: 10.1002/cld.1089 [DOI] [PMC free article] [PubMed] [Google Scholar]
  • 35.Zamani-Siahkali N, Mirshahvalad SA, Pirich C, Beheshti M. Diagnostic performance of [(18)F]F-FDG positron emission tomography (PET) in non-ophthalmic malignant melanoma: A systematic review and meta-analysis of more than 10,000 melanoma patients. Cancers (Basel). 2024;16(1):215. [DOI] [PMC free article] [PubMed] [Google Scholar]
  • 36.Erdi YE. Limits of tumor detectability in nuclear medicine and PET. Mol Imaging Radionucl Ther. 2012;21(1):23–28. doi: 10.4274/Mirt.138 [DOI] [PMC free article] [PubMed] [Google Scholar]
  • 37.Zhou H, Wang Y, Xu H, et al. Noninvasive interrogation of CD8+ T cell effector function for monitoring early tumor responses to immunotherapy. J Clin Invest. 2022;132(16):e161065. [DOI] [PMC free article] [PubMed] [Google Scholar]
  • 38.Dinnes J, Bamber J, Chuchu N, et al. High-frequency ultrasound for diagnosing skin cancer in adults. Cochrane Database Syst Rev. 2018;12(12):Cd013188. [DOI] [PMC free article] [PubMed] [Google Scholar]
  • 39.Zhang G, Lei Y-M, Li N, et al. Ultrasound super-resolution imaging for differential diagnosis of breast masses. Front Oncol. 2022;12:1049991. doi: 10.3389/fonc.2022.1049991 [DOI] [PMC free article] [PubMed] [Google Scholar]
  • 40.Rajadhyaksha M, González S, Zavislan JM, et al. In vivo confocal scanning laser microscopy of human skin II: Advances in instrumentation and comparison with histology. J Invest Dermatol. 1999;113(3):293–303. doi: 10.1046/j.1523-1747.1999.00690.x [DOI] [PubMed] [Google Scholar]
  • 41.Chen KJ, Han Y, Wang Z, et al. Submicron resolution techniques: Multiphoton microscopy in skin disease. Exp Dermatol. 2023;32(10):1613–1623. doi: 10.1111/exd.14899 [DOI] [PubMed] [Google Scholar]
  • 42.Baghban R, Roshangar L, Jahanban-Esfahlan R, et al. Tumor microenvironment complexity and therapeutic implications at a glance. Cell Commun Signal. 2020;18(1):59. doi: 10.1186/s12964-020-0530-4 [DOI] [PMC free article] [PubMed] [Google Scholar]
  • 43.Bussard KM, Mutkus L, Stumpf K, et al. Tumor-associated stromal cells as key contributors to the tumor microenvironment. Breast Cancer Res. 2016;18(1):84. doi: 10.1186/s13058-016-0740-2 [DOI] [PMC free article] [PubMed] [Google Scholar]
  • 44.Gribben J, Rosenwald A, Gascoyne R, et al. Targeting the microenvironment. Leuk Lymphoma. 2010;51(Suppl 1):34–40. doi: 10.3109/10428194.2010.500072 [DOI] [PubMed] [Google Scholar]
  • 45.Papaccio F, Kovacs D, Bellei B, et al. Profiling cancer-associated fibroblasts in melanoma. Int J Mol Sci. 2021;22(14):7255. [DOI] [PMC free article] [PubMed] [Google Scholar]
  • 46.Ria R, Reale A, Castrovilli A, et al. Angiogenesis and progression in human melanoma. Dermatol Res Pract. 2010;2010:185687. doi: 10.1155/2010/185687 [DOI] [PMC free article] [PubMed] [Google Scholar]
  • 47.Kharouf N, Flanagan TW, Hassan S, et al. Tumor microenvironment as a therapeutic target in melanoma treatment. Cancers (Basel). 2023;15(12):3147. [DOI] [PMC free article] [PubMed] [Google Scholar]
  • 48.Kirienko M, Gelardi F, Fiz F, et al. Personalised PET imaging in oncology: An umbrella review of meta-analyses to guide the appropriate radiopharmaceutical choice and indication. Eur J Nucl Med Mol Imaging. 2024;52(1):208–224. doi: 10.1007/s00259-024-06882-9 [DOI] [PMC free article] [PubMed] [Google Scholar]
  • 49.Li LZ, Zhou R, Xu HN, et al. Quantitative magnetic resonance and optical imaging biomarkers of melanoma metastatic potential. Proc Natl Acad Sci USA. 2009;106(16):6608–6613. doi: 10.1073/pnas.0901807106 [DOI] [PMC free article] [PubMed] [Google Scholar]
  • 50.Long WL, Chen F-Y, Huang X-L, et al. Imaging and pathological diagnosis of primary intracranial malignant melanoma: A case report and literature review. Medicine (Baltimore). 2023;102(5):e32767. doi: 10.1097/MD.0000000000032767 [DOI] [PMC free article] [PubMed] [Google Scholar]
  • 51.Varga NN, Gulyás L, Meznerics FA, et al. Diagnostic accuracy of novel optical imaging techniques for melanoma detection: A systematic review and meta-Analysis. Int J Dermatol. 2025:64;1813–1824. doi: 10.1111/ijd.17828 [DOI] [PMC free article] [PubMed] [Google Scholar]
  • 52.Casadonte R, Kriegsmann M, Kriegsmann K, et al. Imaging mass spectrometry-based proteomic analysis to differentiate melanocytic nevi and malignant melanoma. Cancers (Basel). 2021;13(13):3197. [DOI] [PMC free article] [PubMed] [Google Scholar]
  • 53.Belfiore MP, Reginelli A, Russo A, et al. Usefulness of high-frequency ultrasonography in the diagnosis of melanoma: Mini review. Front Oncol. 2021;11:673026. doi: 10.3389/fonc.2021.673026 [DOI] [PMC free article] [PubMed] [Google Scholar]
  • 54.Rajabi-Estarabadi A, Bittar JM, Zheng C, et al. Optical coherence tomography imaging of melanoma skin cancer. Lasers Med Sci. 2019;34(2):411–420. doi: 10.1007/s10103-018-2696-1 [DOI] [PubMed] [Google Scholar]
  • 55.Jing F, Pazhava A, Shachaf C, et al. The role of stromal tumor environment in advancing skin cancer diagnosis and treatment. Int J Dermatol. 2025;64:2019–2028. doi: 10.1111/ijd.17827 [DOI] [PMC free article] [PubMed] [Google Scholar]
  • 56.Lee JT, Herlyn M. Microenvironmental influences in melanoma progression. J Cell Biochem. 2007;101(4):862–872. doi: 10.1002/jcb.21204 [DOI] [PubMed] [Google Scholar]
  • 57.Quail DF, Joyce JA. Microenvironmental regulation of tumor progression and metastasis. Nat Med. 2013;19(11):1423–1437. doi: 10.1038/nm.3394 [DOI] [PMC free article] [PubMed] [Google Scholar]
  • 58.Valkenburg KC, de Groot AE, Pienta KJ. Targeting the tumour stroma to improve cancer therapy. Nat Rev Clin Oncol. 2018;15(6):366–381. doi: 10.1038/s41571-018-0007-1 [DOI] [PMC free article] [PubMed] [Google Scholar]
  • 59.Pickup MW, Mouw JK, Weaver VM. The extracellular matrix modulates the hallmarks of cancer. EMBO Rep. 2014;15(12):1243–1253. doi: 10.15252/embr.201439246 [DOI] [PMC free article] [PubMed] [Google Scholar]
  • 60.Danhier F, Le Breton A, Préat V. RGD-based strategies to target alpha(v) beta(3) integrin in cancer therapy and diagnosis. Mol Pharm. 2012;9(11):2961–2973. doi: 10.1021/mp3002733 [DOI] [PubMed] [Google Scholar]
  • 61.Katalinic A, Waldmann A, Weinstock MA, et al. Does skin cancer screening save lives?: An observational study comparing trends in melanoma mortality in regions with and without screening. Cancer. 2012;118(21):5395–5402. doi: 10.1002/cncr.27566 [DOI] [PubMed] [Google Scholar]
  • 62.Ceder H, Sjoholm Hylen A, Wennberg Larko A-M, et al. Evaluation of electrical impedance spectroscopy as an adjunct to dermoscopy in short-term monitoring of atypical melanocytic lesions. Dermatol Pract Concept. 2016;6(4):1–6. doi: 10.5826/dpc.0604a01 [DOI] [PMC free article] [PubMed] [Google Scholar]
  • 63.Haubner R. Alphavbeta3-integrin imaging: A new approach to characterise angiogenesis? Eur J Nucl Med Mol Imaging. 2006;33(Suppl 1):54–63. doi: 10.1007/s00259-006-0136-0 [DOI] [PubMed] [Google Scholar]
  • 64.Kim KB, Prieto V, Joseph RW, et al. A randomized phase II study of cilengitide (EMD 121974) in patients with metastatic melanoma. Melanoma Res. 2012;22(4):294–301. doi: 10.1097/CMR.0b013e32835312e4 [DOI] [PMC free article] [PubMed] [Google Scholar]
  • 65.Kenny LM, Coombes RC, Oulie I, et al. Phase I trial of the positron-emitting Arg-Gly-Asp (RGD) peptide radioligand 18F-AH111585 in breast cancer patients. J Nucl Med. 2008;49(6):879–886. doi: 10.2967/jnumed.107.049452 [DOI] [PubMed] [Google Scholar]
  • 66.Axelsson R, Bach-Gansmo T, Castell-Conesa J, et al. An open-label, multicenter, phase 2a study to assess the feasibility of imaging metastases in late-stage cancer patients with the alpha v beta 3-selective angiogenesis imaging agent 99mTc-NC100692. Acta Radiol. 2010;51(1):40–46. doi: 10.3109/02841850903273974 [DOI] [PubMed] [Google Scholar]
  • 67.Neto DS, Pantaleão L, De Sá BCS, et al. Alpha-v-beta3 integrin expression in melanocytic nevi and cutaneous melanoma. J Cutan Pathol. 2007;34(11):851–856. doi: 10.1111/j.1600-0560.2007.00730.x [DOI] [PubMed] [Google Scholar]
  • 68.Wu J, Li C, Gensheimer M, et al. Radiological tumor classification across imaging modality and histology. Nat Mach Intell. 2021;3:787–798. doi: 10.1038/s42256-021-00377-0 [DOI] [PMC free article] [PubMed] [Google Scholar]
  • 69.Ajam AA, Xing B, Siddiqui A, et al. Patient satisfaction in outpatient radiology: Effects of modality and patient demographic characteristics. J Patient Exp. 2021;8:23743735211049681. doi: 10.1177/23743735211049681 [DOI] [PMC free article] [PubMed] [Google Scholar]
  • 70.Balasubramaniam AM, Sriraman R, Sindhuja P, et al. Autofluorescence based diagnostic techniques for oral cancer. J Pharm Bioallied Sci. 2015;7(Suppl 2):S374–S377. doi: 10.4103/0975-7406.163456 [DOI] [PMC free article] [PubMed] [Google Scholar]
  • 71.Zaitsev M, Maclaren J, Herbst M. Motion artifacts in MRI: A complex problem with many partial solutions. J Magn Reson Imaging. 2015;42(4):887–901. doi: 10.1002/jmri.24850 [DOI] [PMC free article] [PubMed] [Google Scholar]
  • 72.Deepa R, Arunkumar S, Jayaraj V, Sivasamy A, Healthcare’s new Frontier: AI-driven early cancer detection for improved well-being. AIP Adv. 2023;13(11). [Google Scholar]
  • 73.Xu Y, Wu G, Yuan Z, et al. Deep learning generalization study on optical coherence tomography image denoising. Phys Med Biol. 2025;70. doi: 10.1088/1361-6560/ade840 [DOI] [PubMed] [Google Scholar]
  • 74.Wang S, Pan J, Zhang X, et al. Towards next-generation diagnostic pathology: AI-empowered label-free multiphoton microscopy. Light Sci Appl. 2024;13(1):254. doi: 10.1038/s41377-024-01597-w [DOI] [PMC free article] [PubMed] [Google Scholar]
  • 75.Hu H, Laskin J. Emerging computational methods in mass spectrometry imaging. Adv Sci (Weinh), 2022.;9(34):e2203339. doi: 10.1002/advs.202203339 [DOI] [PMC free article] [PubMed] [Google Scholar]
  • 76.Knoll F, Zbontar J, Sriram A, et al. fastMRI: A publicly available raw k-space and DICOM dataset of knee images for accelerated MR image reconstruction using machine learning. Radiol Artif Intell. 2020;2(1):e190007. doi: 10.1148/ryai.2020190007 [DOI] [PMC free article] [PubMed] [Google Scholar]
  • 77.Xie Z, Baikejiang R, Li T, et al. Generative adversarial network based regularized image reconstruction for PET. Phys Med Biol. 2020;65(12):125016. doi: 10.1088/1361-6560/ab8f72 [DOI] [PMC free article] [PubMed] [Google Scholar]
  • 78.Xiao X, Zhang J, Shao Y, et al. Deep learning-based medical ultrasound image and video segmentation methods: Overview, frontiers, and challenges. Sensors (Basel). 2025;25(8):2361. [DOI] [PMC free article] [PubMed] [Google Scholar]
  • 79.Esteva A, Kuprel B, Novoa RA, et al. Dermatologist-level classification of skin cancer with deep neural networks. Nature. 2017;542(7639):115–118. doi: 10.1038/nature21056 [DOI] [PMC free article] [PubMed] [Google Scholar]
  • 80.Malciu AM, Lupu M, Voiculescu VM. Artificial intelligence-based approaches to reflectance confocal microscopy image analysis in dermatology. J Clin Med. 2022;11(2):429. doi: 10.3390/jcm11020429 [DOI] [PMC free article] [PubMed] [Google Scholar]
  • 81.Maffione AM, Lopci E, Bluemel C, et al. Diagnostic accuracy and impact on management of (18)F-FDG PET and PET/CT in colorectal liver metastasis: A meta-analysis and systematic review. Eur J Nucl Med Mol Imaging. 2015;42(1):152–163. doi: 10.1007/s00259-014-2930-4 [DOI] [PubMed] [Google Scholar]
  • 82.Woo S, Suh CH, Kim SY, et al. Diagnostic performance of magnetic resonance imaging for the detection of bone metastasis in prostate cancer: A systematic review and meta-analysis. Eur Urol. 2018;73(1):81–91. doi: 10.1016/j.eururo.2017.03.042 [DOI] [PubMed] [Google Scholar]
  • 83.Sawatzki M, Güller U, Güsewell S, et al. Contrast-enhanced ultrasound can guide the therapeutic strategy by improving the detection of colorectal liver metastases. J Hepatol. 2021;74(2):419–427. doi: 10.1016/j.jhep.2020.09.036 [DOI] [PubMed] [Google Scholar]
  • 84.Nishio N, van den Berg NS, Martin BA, et al. Photoacoustic molecular imaging for the identification of lymph node metastasis in head and neck cancer using an anti-EGFR antibody-dye conjugate. J Nucl Med. 2021;62(5):648–655. doi: 10.2967/jnumed.120.245241 [DOI] [PMC free article] [PubMed] [Google Scholar]
  • 85.Buchberger AR, DeLaney K, Johnson J, et al. Mass spectrometry imaging: A review of emerging advancements and future insights. Anal Chem. 2018;90(1):240–265. doi: 10.1021/acs.analchem.7b04733 [DOI] [PMC free article] [PubMed] [Google Scholar]
  • 86.Pietkiewicz D, Plewa S, Zaborowski M, et al. Mass spectrometry imaging in gynecological cancers: The best is yet to come. Cancer Cell Int. 2022;22(1):414. doi: 10.1186/s12935-022-02832-3 [DOI] [PMC free article] [PubMed] [Google Scholar]
  • 87.Martin O, Schaarschmidt BM, Kirchner J, et al. PET/MRI versus PET/CT for whole-body staging: Results from a single-center observational study on 1,003 sequential examinations. J Nucl Med. 2020;61(8):1131–1136. doi: 10.2967/jnumed.119.233940 [DOI] [PubMed] [Google Scholar]
  • 88.Morone M, Bali MA, Tunariu N, et al. Whole-body MRI: Current applications in oncology. AJR Am J Roentgenol. 2017;209(6):W336–w349. doi: 10.2214/AJR.17.17984 [DOI] [PubMed] [Google Scholar]
  • 89.Lao IH, Chao H, Wang Y-J, et al. Computed tomography has low sensitivity for the diagnosis of early colon cancer. Colorectal Dis. 2013;15(7):807–811. doi: 10.1111/codi.12140 [DOI] [PubMed] [Google Scholar]
  • 90.Park CKS, Trumpour T, Aziz A, et al. Cost-effective, portable, patient-dedicated three-dimensional automated breast ultrasound for point-of-care breast cancer screening. Sci Rep. 2023;13(1):14390. doi: 10.1038/s41598-023-41424-7 [DOI] [PMC free article] [PubMed] [Google Scholar]
  • 91.Iftimia N, Peterson G, Chang EW, et al. Combined reflectance confocal microscopy-optical coherence tomography for delineation of basal cell carcinoma margins: An ex vivo study. J Biomed Opt. 2016;21(1):16006. doi: 10.1117/1.JBO.21.1.016006 [DOI] [PMC free article] [PubMed] [Google Scholar]
  • 92.Wan B, Ganier C, Du-Harpur X, et al. Applications and future directions for optical coherence tomography in dermatology. Br J Dermatol. 2021;184(6):1014–1022. doi: 10.1111/bjd.19553 [DOI] [PubMed] [Google Scholar]
  • 93.Brenner DJ, Hall EJ. Computed tomography–an increasing source of radiation exposure. N Engl J Med. 2007;357(22):2277–2284. doi: 10.1056/NEJMra072149 [DOI] [PubMed] [Google Scholar]

Articles from Technology in Cancer Research & Treatment are provided here courtesy of SAGE Publications

RESOURCES